Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3698 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.6878. Min Act: -0.1700
Data Index: 7765279 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5940. Min Act: -0.1700
Data Index: 4478442 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5940. Min Act: -0.1700
Data Index: 1959370 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5628. Min Act: -0.1700
Data Index: 578957 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5628. Min Act: -0.1700
Data Index: 4765602 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5628. Min Act: -0.1700
Data Index: 2552958 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5315. Min Act: -0.1700
Data Index: 703516 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.5003. Min Act: -0.1700
Data Index: 303124 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1019663 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4690. Min Act: -0.1700
Data Index: 1922692 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4378. Min Act: -0.1700
Data Index: 3433217 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4378. Min Act: -0.1700
Data Index: 551382 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4065. Min Act: -0.1700
Data Index: 561915 (Open Web Text)
Max Activating Token Index: 320
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.3753. Min Act: -0.1700
Data Index: 1134483 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4065. Min Act: -0.1700
Data Index: 4752187 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4065. Min Act: -0.1700
Data Index: 1201751 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4065. Min Act: -0.1700
Data Index: 3032273 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.3753. Min Act: -0.1700
Data Index: 613832 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.3753. Min Act: -0.1700
Data Index: 5999404 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.6878. Min Range: -5.6878
Max Act: 5.4065. Min Act: -0.1700
Data Index: 3552579 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #19